el-grammar 0.3.5

Pure-Rust DFA/regular-grammar token masking (Grammar Constraint context).

Coverage
66.67%
8 out of 12 items documented0 out of 10 items with examples
Size
Source code size: 9.06 kB This is the summed size of all the files inside the crates.io package for this release.
Documentation size: 369.96 kB This is the summed size of all files generated by rustdoc for all configured targets
Ø build duration
this release: 4s Average build duration of successful builds.
all releases: 3s Average build duration of successful builds in releases after 2024-10-23.
Links
crates.io
Dependencies
Versions
Owners

el-grammar — pure-Rust DFA token masking for grammar-constrained decoding (Grammar Constraint context, docs/ddd/bounded-contexts/04).

A grammar is compiled to a deterministic automaton over token ids (the alphabet). Each decode step, the masker replays the committed tokens to find the current state and allows only tokens with a valid transition — the exact token-level masking mechanism that XGrammar/llguidance implement, here for regular grammars in pure Rust.

Scope: this covers regular grammars over an explicit token alphabet. Full context-free / JSON-schema grammars + a real tokenizer environment are the el-grammar-llguidance production scale-up.